mlsanityData to 7 Oct 2026

Histogram-Equalized Quantization for logic-gated Residual Neural Networks

arXiv 2501.04517 ↗First posted 8 Jan 2025cs.LG cs.ARcited by 4

Not on the map. Why?

Abstract (arXiv)

Adjusting the quantization according to the data or to the model loss seems mandatory to enable a high accuracy in the context of quantized neural networks. This work presents Histogram-Equalized Quantization (HEQ), an adaptive framework for linear symmetric quantization. HEQ automatically adapts the quantization thresholds using a unique step size optimization. We empirically show that HEQ achieves state-of-the-art performances on CIFAR-10. Experiments on the STL-10 dataset even show that HEQ enables a proper training of our proposed logic-gated (OR, MUX) residual networks with a higher accuracy at a lower hardware complexity than previous work.

Key facts. Cited by 4 papers in the map (data through 7 Oct 2026). Builds on 21 of its 37 references that are in the map. First posted on arXiv 8 Jan 2025.

Builds on

21 of 37 references.

References · 21

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2014Very Deep Convolutional Networks for Large-Scale Image Recognitioncited by 15,267
  3. 2015Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shiftcited by 6,979
  4. 2015Deep Compression: Compressing Deep Neural Networks with Pruning, Trained Quantization and Huffman Codingcited by 2,291
  5. 2013Estimating or Propagating Gradients Through Stochastic Neurons for Conditional Computationcited by 2,031
  6. 2017Improved Regularization of Convolutional Neural Networks with Cutoutcited by 1,623
  7. 2019Learned Step Size Quantizationcited by 604
  8. 2016DoReFa-Net: Training Low Bitwidth Convolutional Neural Networks with Low Bitwidth Gradientscited by 557
  9. 2016Quantized Neural Networks: Training Neural Networks with Low Precision Weights and Activationscited by 413
  10. 2017Residual Attention Network for Image Classificationcited by 385
  11. 2018LQ-Nets: Learned Quantization for Highly Accurate and Compact Deep Neural Networkscited by 272
  12. 2018Bi-Real Net: Enhancing the Performance of 1-bit CNNs With Improved Representational Capability and Advanced Training Algorithmcited by 233
9 more
  1. 2016Trained Ternary Quantizationcited by 203
  2. 2016Ternary Weight Networkscited by 195
  3. 2016Convolutional Neural Networks using Logarithmic Data Representationcited by 97
  4. 2020HAWQV3: Dyadic Neural Network Quantizationcited by 59
  5. 2019MoBiNet: A Mobile Binary Network for Image Classificationcited by 15
  6. 2016Effective Quantization Methods for Recurrent Neural Networkscited by 14
  7. 2018Effective Quantization Approaches for Recurrent Neural Networkscited by 10
  8. 2020ChewBaccaNN: A Flexible 223 TOPS/W BNN Acceleratorcited by 7
  9. 2022Soft Threshold Ternary Networkscited by 2

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 3; 2026: 1.

4 papers.

  1. 2025Automatic Grid Updates for Kolmogorov-Arnold Networks using Layer Histogramscited by 3
  2. 2025Towards Experience Replay for Class-Incremental Learning in Fully-Binary Networkscited by 0
  3. 2025End-to-end fully-binarized network design: from Generic Learned Thermometer to Block Pruningcited by 0
  4. 2026Soft Quantization: Model Compression Via Weight Couplingcited by 0